283 citations · 814 across the 69 of their papers we have counts for
26 papers · 1 filter
Polaris: Scaling Up Instruction-Guided Image Generation Towards Millions of Personalized Style Needs
Zhi-Kai Chen, Jun-Peng Jiang, Jun-Jie Tao +2
Users increasingly expect image generation models to quickly adapt to highly diverse and personalized requirements, such as producing images with distinctive styles or characterist…
BOFA: Bridge-Layer Orthogonal Low-Rank Fusion for CLIP-Based Class-Incremental Learning
Lan Li, Tao Hu, Da-Wei Zhou +3
Class-Incremental Learning (CIL) aims to continually learn new categories without forgetting previously acquired knowledge. Vision-language models such as CLIP offer strong transfe…
Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation
Zhi-Kai Chen, Jun-Peng Jiang, Han-Jia Ye +1
Autoregressive (AR) image generation models are capable of producing high-fidelity images but often suffer from slow inference due to their inherently sequential, token-by-token de…
Task-Agnostic Guided Feature Expansion for Class-Incremental Learning
Bowen Zheng, Da-Wei Zhou, Han-Jia Ye +1
The ability to learn new concepts while preserve the learned knowledge is desirable for learning systems in Class-Incremental Learning (CIL). Recently, feature expansion of the mod…
External Knowledge Injection for CLIP-Based Class-Incremental Learning
Da-Wei Zhou, Kai-Wen Li, Jingyi Ning +3
Class-Incremental Learning (CIL) enables learning systems to continuously adapt to evolving data streams. With the advancement of pre-training, leveraging pre-trained vision-langua…
Dual Consolidation for Pre-Trained Model-Based Domain-Incremental Learning
Da-Wei Zhou, Zi-Wen Cai, Han-Jia Ye +2
Domain-Incremental Learning (DIL) involves the progressive adaptation of a model to new concepts across different domains. While recent advances in pre-trained models provide a sol…
Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification
Chao Yi, Lu Ren, De-Chuan Zhan +1
CLIP showcases exceptional cross-modal matching capabilities due to its training on image-text contrastive learning tasks. However, without specific optimization for unimodal scena…
TV100: A TV Series Dataset that Pre-Trained CLIP Has Not Seen
Da-Wei Zhou, Zhi-Hong Qi, Han-Jia Ye +1
The era of pre-trained models has ushered in a wealth of new insights for the machine learning community. Among the myriad of questions that arise, one of paramount importance is:…
Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning
Da-Wei Zhou, Hai-Long Sun, Han-Jia Ye +1
Class-Incremental Learning (CIL) requires a learning system to continually learn new classes without forgetting. Despite the strong performance of Pre-Trained Models (PTMs) in CIL,…
Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration
Qi-Wei Wang, Da-Wei Zhou, Yi-Kai Zhang +2
Real-world scenarios are usually accompanied by continuously appearing classes with scare labeled samples, which require the machine learning model to incrementally learn new class…
Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising
Fu-Yun Wang, Wenshuo Chen, Guanglu Song +3
Leveraging large-scale image-text datasets and advancements in diffusion models, text-driven generative models have made remarkable strides in the field of image generation and edi…
Learning without Forgetting for Vision-Language Models
Da-Wei Zhou, Yuanhan Zhang, Yan Wang +4
Class-Incremental Learning (CIL) or continual learning is a desired capability in the real world, which requires a learning system to adapt to new tasks without forgetting former o…
Class-Incremental Learning: A Survey
Da-Wei Zhou, Qi-Wei Wang, Zhi-Hong Qi +3
Deep models, e.g., CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in…
Dual-Stream Transformer for Generic Event Boundary Captioning
Xin Gu, Hanhua Ye, Guang Chen +3
This paper describes our champion solution for the CVPR2022 Generic Event Boundary Captioning (GEBC) competition. GEBC requires the captioning model to have a comprehension of inst…
Generalized Knowledge Distillation via Relationship Matching
Han-Jia Ye, Su Lu, De-Chuan Zhan
The knowledge of a well-trained deep neural network (a.k.a. the "teacher") is valuable for learning similar tasks. Knowledge distillation extracts knowledge from the teacher and in…
Identifying Ambiguous Similarity Conditions via Semantic Matching
Han-Jia Ye, Yi Shi, De-Chuan Zhan
Rich semantics inside an image result in its ambiguous relationship with others, i.e., two images could be similar in one condition but dissimilar in another. Given triplets like "…
FOSTER: Feature Boosting and Compression for Class-Incremental Learning
Fu-Yun Wang, Da-Wei Zhou, Han-Jia Ye +1
The ability to learn new concepts continually is necessary in this ever-changing world. However, deep neural networks suffer from catastrophic forgetting when learning new categori…
Forward Compatible Few-Shot Class-Incremental Learning
Da-Wei Zhou, Fu-Yun Wang, Han-Jia Ye +3
Novel classes frequently arise in our dynamically changing world, e.g., new users in the authentication system, and a machine learning model should recognize new classes without fo…
Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks
Da-Wei Zhou, Han-Jia Ye, Liang Ma +3
New classes arise frequently in our ever-changing world, e.g., emerging topics in social media and new types of products in e-commerce. A model should recognize new classes and mea…
Hierarchical Modular Network for Video Captioning
Hanhua Ye, Guorong Li, Yuankai Qi +3
Video captioning aims to generate natural language descriptions according to the content, where representation learning plays a crucial role. Existing methods are mainly developed…
Co-Transport for Class-Incremental Learning
Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan
Traditional learning systems are trained in closed-world for a fixed number of classes, and need pre-collected datasets in advance. However, new classes often emerge in real-world…
Few-Shot Learning with a Strong Teacher
Han-Jia Ye, Lu Ming, De-Chuan Zhan +1
Few-shot learning (FSL) aims to generate a classifier using limited labeled examples. Many existing works take the meta-learning approach, constructing a few-shot learner that can…
Few-Shot Action Recognition with Compromised Metric via Optimal Transport
Su Lu, Han-Jia Ye, De-Chuan Zhan
Although vital to computer vision systems, few-shot action recognition is still not mature despite the wide research of few-shot image classification. Popular few-shot learning alg…
Learning Placeholders for Open-Set Recognition
Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan
Traditional classifiers are deployed under closed-set setting, with both training and test classes belong to the same set. However, real-world applications probably face the input…